Towards Real-time Probabilistic Evaluation of Situation Awareness from Human Gaze in Human-Robot Interaction

Human attention processes play a major role for optimization in human-robot interaction (HRI). This work describes a novel methodology to measure situation awareness in real-time from gaze interaction with scene objects of interest using eye tracking glasses and 3D gaze analysis. A probabilistic framework of uncertainty considers coping with measurement errors in eye and position tracking. Comprehensive experiments on HRI were conducted with tasks including handover in a lab based prototypical manufacturing environment. The methodology is proven to predict a standard measure of situation awareness (SAGAT) in real-time and will open new opportunities for human factors based performance optimization in HRI applications.